berndf commited on
Commit
f5bc732
·
verified ·
1 Parent(s): 841a8a7

modified some data sets to be more diverse (e.g. different industries)

Browse files
Files changed (1) hide show
  1. app.py +19 -19
app.py CHANGED
@@ -44,29 +44,29 @@ BASE_SETS = {
44
  "boxing","skiing","snowboarding","surfing","skateboarding","karate","judo","fencing","rowing","badminton",
45
  "cricket","table tennis","gymnastics","hockey","climbing"
46
  ],
47
- "ai concepts": [
 
48
  "neural network","transformer","embedding","fine-tuning","vector database",
49
- "retrieval-augmented generation","prompt","agent","context window","reasoning",
50
- "gradient descent","supervised learning","unsupervised learning","reinforcement learning","memory",
51
- "self-attention","inference","hallucination","pretraining","chain of thought"
 
52
  ],
53
- "tech companies": [
54
- "OpenAI","Google","Microsoft","Anthropic","Meta","Amazon","Apple","NVIDIA","IBM","Databricks",
55
- "Snowflake","Hugging Face","Cohere","Mistral","xAI","Adept","Runway","Perplexity","Scale AI","DeepMind"
 
 
 
 
56
  ],
57
  "finance": [
58
- "equity","bond","derivative","liquidity","leverage","inflation","dividend","yield","credit risk","portfolio",
59
- "asset","liability","capital","interest rate","valuation","revenue","profit","return on investment","hedge","market"
60
- ],
61
- "buzzwords": [
62
- "innovation","disruption","ecosystem","synergy","scalability","automation","data-driven","agility","transformation","cloud",
63
- "blockchain","AI","machine learning","quantum computing","metaverse","sustainability","fintech","cybersecurity","big data","LLM"
64
- ],
65
- "ai pioneers": [
66
- "Geoffrey Hinton","Yann LeCun","Yoshua Bengio","Andrew Ng","Demis Hassabis",
67
- "Sam Altman","Dario Amodei","Fei-Fei Li","Sebastian Raschka","Jensen Huang",
68
- "Ilya Sutskever","Jeff Dean","Ian Goodfellow","Chris Olah","Andrej Karpathy",
69
- "Lex Fridman","Richard Sutton","Emad Mostaque","Timnit Gebru","Elon Musk"
70
  ],
71
  }
72
 
 
44
  "boxing","skiing","snowboarding","surfing","skateboarding","karate","judo","fencing","rowing","badminton",
45
  "cricket","table tennis","gymnastics","hockey","climbing"
46
  ],
47
+ "ai_cs_concepts": [
48
+ # AI concepts (10)
49
  "neural network","transformer","embedding","fine-tuning","vector database",
50
+ "retrieval-augmented generation","prompt","agent","inference","self-attention",
51
+ # Classical CS concepts (10)
52
+ "algorithm","data structure","compiler","register","stack",
53
+ "queue","binary tree","hash table","database","quicksort"
54
  ],
55
+ "tech_companies": [
56
+ # AI / Tech (7)
57
+ "OpenAI","Anthropic","Google","Microsoft","Meta","NVIDIA","Hugging Face",
58
+ # Automotive (7)
59
+ "Tesla","BMW","Mercedes-Benz","Volkswagen","Toyota","Ford","Volvo",
60
+ # Pharma / Life Science (6)
61
+ "Pfizer","Roche","Novartis","Johnson & Johnson","Bayer","BioNTech"
62
  ],
63
  "finance": [
64
+ # Core finance terms (10)
65
+ "equity","bond","derivative","liquidity","leverage",
66
+ "portfolio","valuation","capital","revenue","profit",
67
+ # Currencies (10)
68
+ "US dollar","euro","British pound","Japanese yen","Swiss franc",
69
+ "Chinese yuan","Canadian dollar","Australian dollar","Indian rupee","Brazilian real"
 
 
 
 
 
 
70
  ],
71
  }
72